© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 10345
    Prev
    Next
    INDEX
    Explanations

    business, professional, and AI contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     desarrollo
    1.63
    及ひ
    1.57
     ২০
    1.56
     dédié
    1.55
     baseUrl
    1.52
    ওয়ান
    1.50
     sene
    1.49
     ্
    1.48
     pandemi
    1.47
    𝘪
    1.47
    POSITIVE LOGITS
    뇰
    1.58
     dissatisfied
    1.51
     ہوں
    1.50
     puzzled
    1.47
     gloom
    1.44
     foes
    1.43
     bewildered
    1.40
    Č
    1.40
     merely
    1.40
     anguish
    1.39
    Activations Density 1.635%

    No Known Activations